Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for operating an artificial neural network

A technology of artificial neural network and convolution operation, applied in the field of artificial neural network to achieve the effect of improving artificial neural network

Pending Publication Date: 2020-11-03
ROBERT BOSCH GMBH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Here, normalization of input data can be computationally intensive and / or time-consuming and requires powerful hardware to perform

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for operating an artificial neural network
  • Method for operating an artificial neural network
  • Method for operating an artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] figure 1 An artificial neural network 10 according to one embodiment of the invention is shown. exist figure 1 The artificial neural network 10 shown in exemplarily is implemented as a multilayer neural network 10 .

[0042] For example, in the field of object recognition in motor vehicles, the neural network 10 can be used to interpret image data. The neural network 10 can, for example, be coupled to a memory device 11 and / or can have a memory device 11 for storing image data. The image data can be recorded, for example, by means of a camera of the motor vehicle and can be stored in the memory device 11 for further processing and / or interpretation by the neural network 10 . The image data can have one or more images, which can be supplied to neural network 10 and / or fed into neural network 10 .

[0043] The artificial neural network 10 has an input layer 12a and / or a first layer 12a, an input matrix I 0 is provided to the input layer and / or the first layer. Typic...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for operating an artificial neural network (10) which comprises at least one convolution layer (12a-c), which is configured to transform an input matrix (I) of the convolution layer (12a-c) into an output matrix (A) on the basis of a convolution operation and a shift operation. The method comprises determining at least one first and one second normalization quantity on the basis of entries in the input matrix (I) and / or on the basis of a training data set, determining a modified filter matrix ( / ) on the basis of an original filter matrix (f) and on the basis of at least one of the first normalization quantity and the second normalization quantity, and determining a modified shift matrix (5) on the basis of an original shift matrix (b) and on the basis of at least one of the first normalization quantity and the second normalization quantity. The method further comprises transforming the input matrix (I) into the output matrix (A) by applying the modified filter matrix ( / ) and the modified shift matrix (5). In this manner, it is possible advantageously to combine a normalization operation with the convolution operation and the shift operation.

Description

technical field [0001] The present invention relates generally to the field of artificial intelligence. In particular, the invention relates to a method for operating an artificial neural network, which can be used, for example, for object recognition in a vehicle, and to an artificial neural network. Background technique [0002] For training an artificial neural network, in particular a multilayer and / or convolutional neural network, the training data (eg training images) supplied to the neural network are usually normalized and / or normalized. This can also be used to homogenize the training data of the training data set. Objects and / or features present in the training data can also be highlighted and / or emphasized in some cases by the normalization. [0003] After training the neural network and / or during the operation of the trained neural network (this is also often referred to as inference), the input data provided to the neural network for interpretation and / or clas...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04
CPCG06N3/08G06N3/045G06F17/16G06F17/18
Inventor J·E·M·梅纳特R·M·克勒P·彼得里齐奥
Owner ROBERT BOSCH GMBH